Search

Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently update them to accommodate previously unseen data. To solve these problems, we propose an incremental learning framework based on a grow-and-prune neural network synthesis paradigm. When new data arrive, the neural network first grows new connections based on the gradients to increase the network capacity to accommodate new data. Then, the framework iteratively prunes away connections based on the magnitude of weights to enhance network compactness, and hence recover efficiency. Finally, the model rests at a lightweight DNN that is both ready for inference and suitable for future grow-and-prune updates. The proposed framework improves accuracy, shrinks network size, and significantly reduces the additional training cost for incoming data compared to conventional approaches, such as training from scratch and network fine-tuning. For the LeNet-300-100 (LeNet-5) neural network architectures derived for the MNIST dataset, the framework reduces training cost by up to 64% (67%), 63% (63%), and 69% (73%) compared to training from scratch, network fine-tuning, and grow-and-prune from scratch, respectively. For the ResNet-18 architecture derived for the ImageNet dataset (DeepSpeech2 for the AN4 dataset), the corresponding training cost reductions against training from scratch, network fine-tunning, and grow-and-prune from scratch are 64% (67%), 60% (62%), and 72% (71%), respectively. Our derived models contain fewer network parameters but achieve higher accuracy relative to conventional baselines.

As an effective and efficient discriminative learning method, Broad Learning System (BLS) has received increasing attention due to its outstanding performance in various regression and classification problems. However, the standard BLS is derived under the minimum mean square error (MMSE) criterion, which is, of course, not always a good choice due to its sensitivity to outliers. To enhance the robustness of BLS, we propose in this work to adopt the maximum correntropy criterion (MCC) to train the output weights, obtaining a correntropy based broad learning system (C-BLS). Thanks to the inherent superiorities of MCC, the proposed C-BLS is expected to achieve excellent robustness to outliers while maintaining the original performance of the standard BLS in Gaussian or noise-free environment. In addition, three alternative incremental learning algorithms, derived from a weighted regularized least-squares solution rather than pseudoinverse formula, for C-BLS are developed.With the incremental learning algorithms, the system can be updated quickly without the entire retraining process from the beginning, when some new samples arrive or the network deems to be expanded. Experiments on various regression and classification datasets are reported to demonstrate the desirable performance of the new methods.

The continual learning (CL) paradigm aims to enable neural networks to learn tasks continually in a sequential fashion. The fundamental challenge in this learning paradigm is catastrophic forgetting previously learned tasks when the model is optimized for a new task, especially when their data is not accessible. Current architectural-based methods aim at alleviating the catastrophic forgetting problem but at the expense of expanding the capacity of the model. Regularization-based methods maintain a fixed model capacity; however, previous studies showed the huge performance degradation of these methods when the task identity is not available during inference (e.g. class incremental learning scenario). In this work, we propose a novel architectural-based method referred as SpaceNet for class incremental learning scenario where we utilize the available fixed capacity of the model intelligently. SpaceNet trains sparse deep neural networks from scratch in an adaptive way that compresses the sparse connections of each task in a compact number of neurons. The adaptive training of the sparse connections results in sparse representations that reduce the interference between the tasks. Experimental results show the robustness of our proposed method against catastrophic forgetting old tasks and the efficiency of SpaceNet in utilizing the available capacity of the model, leaving space for more tasks to be learned. In particular, when SpaceNet is tested on the well-known benchmarks for CL: split MNIST, split Fashion-MNIST, and CIFAR-10/100, it outperforms regularization-based methods by a big performance gap. Moreover, it achieves better performance than architectural-based methods without model expansion and achieved comparable results with rehearsal-based methods, while offering a huge memory reduction., Published in Neurocomputing Journal

The online analysis of multi-way data stored in a tensor has become an essential tool for capturing the underlying structures and extracting the sensitive features that can be used to learn a predictive model. However, data distributions often evolve with time and a current predictive model may not be sufficiently representative in the future. Therefore, incrementally updating the tensor-based features and model coefficients are required in such situations. A new efficient tensor-based feature extraction, named Nesterov Stochastic Gradient Descent (NeSGD), is proposed for online (CP) decomposition. According to the new features obtained from the resultant matrices of NeSGD, a new criterion is triggered for the updated process of the online predictive model. Experimental evaluation in the field of structural health monitoring using laboratory-based and real-life structural datasets shows that our methods provide more accurate results compared with existing online tensor analysis and model learning. The results showed that the proposed methods significantly improved the classification error rates, were able to assimilate the changes in the positive data distribution over time, and maintained a high predictive accuracy in all case studies.

Multi-Source Information Fusion (MSIF) is a comprehensive and interdisciplinary subject, and is referred to as, multi-sensor information fusion which was originated in the 1970s. Nowadays, the types and updates of data are becoming more multifarious and frequent, which bring new challenges for information fusion to deal with the multi-source data. Consequently, the construction of MSIF models suitable for different scenarios and the application of different fusion technologies are the core problems that need to be solved urgently. Rough set theory (RST) provides a computing paradigm for uncertain data modeling and reasoning, especially for classification issues with noisy, inaccurate or incomplete data. Furthermore, due to the rapid development of MSIF in recent years, the methodologies of learning under RST are becoming increasingly mature and systematic, unveiling a framework which has not been mentioned in the literature. In order to better clarify the approaches and application of MSIF in RST research community, this paper reviews the existing models and technologies from the perspectives of MSIF model (i.e., homogeneous and heterogeneous MSIF model), multi-view rough sets information fusion model (i.e., multi-granulation, multi-scale and multi-view decisions information fusion models), parallel computing information fusion model, incremental learning fusion technology and cluster ensembles fusion technology. Finally, RST based MSIF related research directions and challenges are also covered and discussed. By providing state-of-the-art understanding in specialized literature, this survey will directly help researchers understand the research developments of MSIF under RST.

Robotic visual systems operating in the wild must act in unconstrained scenarios, under different environmental conditions while facing a variety of semantic concepts, including unknown ones. To this end, recent works tried to empower visual object recognition methods with the capability to i) detect unseen concepts and ii) extended their knowledge over time, as images of new semantic classes arrive. This setting, called Open World Recognition (OWR), has the goal to produce systems capable of breaking the semantic limits present in the initial training set. However, this training set imposes to the system not only its own semantic limits, but also environmental ones, due to its bias toward certain acquisition conditions that do not necessarily reflect the high variability of the real-world. This discrepancy between training and test distribution is called domain-shift. This work investigates whether OWR algorithms are effective under domain-shift, presenting the first benchmark setup for assessing fairly the performances of OWR algorithms, with and without domain-shift. We then use this benchmark to conduct analyses in various scenarios, showing how existing OWR algorithms indeed suffer a severe performance degradation when train and test distributions differ. Our analysis shows that this degradation is only slightly mitigated by coupling OWR with domain generalization techniques, indicating that the mere plug-and-play of existing algorithms is not enough to recognize new and unknown categories in unseen domains. Our results clearly point toward open issues and future research directions, that need to be investigated for building robot visual systems able to function reliably under these challenging yet very real conditions. Code available at https://github.com/DarioFontanel/OWR-VisualDomains, RAL/ICRA 2021

The development of 3D object recognition often requires a huge amount of data in the training process, especially when deep learning methods are involved so that the training can be convergent. The problem is that the availability of free 3D object datasets is usually quite limited, so some researchers have proposed several techniques to overcome this problem. In this work, we propose a novel algorithm, making use of angular resolutions and convolutional neural networks for 3D object recognition, and it collects image shapes or contours from real objects by placing them on a rotating display to record the appearances from multiple angular views. The chosen angular resolution is in the range of 0-180 degrees, and the selection of viewing angle is done by a binary search. We have conducted a comparative experiment on the accuracy of 6 well-known network architectures, including GoogleNet, CaffeNet, SqueezeNet, ResNet18, ResNet32, and ResNet50, to see how far these architecture networks can adapt to the angular resolution techniques that we propose for the classification of objects outside the lab environment. We also propose another way with the use of incremental learning, where we integrate our proposed method that uses GoogleNet model with two existing weights pre-trained models, i.e., AlexNet and VGG16. In other words, our proposed method helps address the limitations of other models with the weights of existing pre-trained methods to recognize new classes that were not recognized.

Concept-cognitive learning (CCL) is an emerging field of concerning incremental concept learning and dynamic knowledge processing in the context of dynamic environments. Although CCL has been widely researched in theory, the existing studies of CCL have one problem: the concepts obtained by CCL systems do not have generalization ability. In the meantime, the existing incremental algorithms still face some challenges that: 1) classifiers have to adapt gradually and 2) the previously acquired knowledge should be efficiently utilized. To address these problems, based on the advantage that CCL can naturally integrate new data into itself for enhancing flexibility of concept learning, we first propose a new CCL model (CCLM) to extend the classical methods of CCL, which is not only a new classifier but also good at incremental learning. Unlike the existing CCL systems, the theory of CCLM is mainly based on a formal decision context rather than a formal context. In learning concepts from dynamic environments, we show that CCLM can naturally incorporate new data into itself with a sufficient theoretical guarantee for incremental learning. For classification task and knowledge storage, our results on various data sets demonstrate that CCLM can simultaneously: 1) achieve the state-of-the-art static and dynamic classification task and 2) directly accomplish preservation of previously acquired knowledge (or concepts) under dynamic environments.

The Internet of Things is transforming our society, providing new services that improve the quality of life and resource management. These applications are based on ubiquitous networks of multiple distributed devices, with limited computing resources and power, capable of collecting and storing data from heterogeneous sources in real-time. To avoid network saturation and high delays, new architectures such as fog computing are emerging to bring computing infrastructure closer to data sources. Additionally, new data centers are needed to provide real-time Big Data and data analytics capabilities at the edge of the network, where energy efficiency needs to be considered to ensure a sustainable and effective deployment in areas of human activity. In this research, we present an IoT model based on the principles of Model-Based Systems Engineering defined using the Discrete Event System Specification formalism. The provided mathematical formalism covers the description of the entire architecture, from IoT devices to the processing units in edge data centers. Our work includes the location-awareness of user equipment, network, and computing infrastructures to optimize federated resource management in terms of delay and power consumption. We present an effective framework to assist the dimensioning and the dynamic operation of IoT data stream analytics applications, demonstrating our contributions through a driving assistance use case based on real traces and data.

This study introduces an ensemble-based personalized human activity recognition method relying on incremental learning, which is a method for continuous learning, that can not only learn from streaming data but also adapt to different contexts and changes in context. This adaptation is based on a novel weighting approach which gives bigger weight to those base models of the ensemble which are the most suitable to the current context. In this article, contexts are different body positions for inertial sensors. The experiments are performed in two scenarios: (S1) adapting model to a known context, and (S2) adapting model to a previously unknown context. In both scenarios, the models had to also adapt to the data of previously unknown person, as the initial user-independent dataset did not include any data from the studied user. In the experiments, the proposed ensemble-based approach is compared to non-weighted personalization method relying on ensemble-based classifier and to static user-independent model. Both ensemble models are experimented using three different base classifiers (linear discriminant analysis, quadratic discriminant analysis, and classification and regression tree). The results show that the proposed ensemble method performs much better than non-weighted ensemble model for personalization in both scenarios no matter which base classifier is used. Moreover, the proposed method outperforms user-independent models. In scenario 1, the error rate of balanced accuracy using user-independent model was 13.3%, using non-weighted personalization method 13.8%, and using the proposed method 6.4%. The difference is even bigger in scenario 2, where the error rate using user-independent model is 36.6%, using non-weighted personalization method 36.9%, and using the proposed method 14.1%. In addition, F1 scores also show that the proposed method performs much better in both scenarios that the rival methods. Moreover, as a side result, it was noted that the presented method can also be used to recognize body position of the sensor.

Lifelong learning is still a great challenge for cognitive robots since the continuous streaming data they encounter is usually enormous and no-stationary. Traditional cognitive methods suffer from large storage and computation consumption in this situation. Therefore, we propose a self-organizing and reflecting cognitive network (SORCN) to realize robotic lifelong cognitive development through incremental learning and regular reflecting. The network integrates a self-organizing incremental neural network (SOINN) with a modified CFS clustering algorithm. SOINN develops concise object concepts to alleviate storage consumption. Moreover, we modify SOINN by an efficient competitive method based on reflection results to reduce the learning computation. The modified CFS clustering algorithm is designed for reflecting knowledge learned by SOINN periodically. It improves the traditional CFS as a three-step clustering method including clustering, merging and splitting. Specifically, an autonomous center selection strategy is employed for CFS to cater to online learning. Moreover, a series of cluster merging and splitting strategies are proposed to enable CFS to cluster data incrementally and improve its clustering effect. Additionally, the reflection results are utilized to adjust the topological structure of SOINN and guide the future learning. Experimental results demonstrate that SORCN can achieve better learning effectiveness and efficiency over several state-of-art algorithms.

In this paper, we propose an efficient algorithm to accelerate the existing Broad Learning System (BLS) algorithm for new added nodes. The existing BLS algorithm computes the output weights from the pseudoinverse with the ridge regression approximation, and updates the pseudoinverse iteratively. As a comparison, the proposed BLS algorithm computes the output weights from the inverse Cholesky factor of the Hermitian matrix in the calculation of the pseudoinverse, and updates the inverse Cholesky factor efficiently. Since the Hermitian matrix in the definition of the pseudoinverse is smaller than the pseudoinverse, the proposed BLS algorithm can reduce the computational complexity, and usually requires less than $\frac {2}{3}$ of complexities with respect to the existing BLS algorithm. Our experiments on the Modified National Institute of Standards and Technology (MNIST) dataset show that the speedups in accumulative training time and each additional training time of the proposed BLS over the existing BLS are 24.81%~ 37.99% and 36.45%~ 58.96%, respectively, and the speedup in total training time is 37.99%. In our experiments, the proposed BLS and the existing BLS both achieve the same testing accuracy when the tiny differences (≤ 0.05%) caused by the numerical errors are neglected, and the above-mentioned tiny differences and numerical errors become zeroes and ignorable, respectively, when the ridge parameter is not too small.

With the exponential rise of the number of IoT devices, the amount of data being produced is massive. Thus, it is unfeasible to send all the raw data directly to the cloud for processing, especially for data that is high dimensional. Training deep learning models incrementally evolves the model over time and eliminates the need to statically training the models with all the data. However, the integration of class incremental learning and the Internet of Things (IoT) is a new concept and is not yet mature. In the context of IoT and deep learning, the transmission cost of data in the edge-cloud architecture is a challenge. We demonstrate a novel sample selection method that discards certain training images on the IoT edge device that reduces transmission cost and still maintains class incremental learning performance. It can be unfeasible to transmit all parameters of a trained model back to the IoT edge device. Therefore, we propose an algorithm to find only the useful parameters of a trained model in an efficient way to reduce the transmission cost from the cloud to the edge devices. Results show that our proposed methods can effectively perform class-incremental learning in an edge-cloud setting.

Human activity recognition (HAR) based on wearable sensors has attracted significant research attention in recent years due to its advantages in availability, accuracy, and privacy-friendliness. HAR baseline model is essentially a general-purpose classifier trained to recognized multiple activity patterns of most user types. It provides the input for subsequent steps of model personalization. Training a good baseline model is of fundamental importance because it has significant impacts on the ultimate HAR accuracy. In practice, baseline model training in HAR is a non-trivial problem that faces two challenges: insufficient training data and biased training data. This paper proposes a novel baseline model training scheme to tackle the two challenges using Deep InfoMax (DIM)-based unsupervised feature extraction and Broad Learning System (BLS)-based incremental learning, respectively. Experimental results demonstrate that the proposed scheme outperform conventional methods in terms of overall accuracy, computational efficiency, and the ability to adapt to dynamic scenarios with changing data characteristics.

The broad learning system (BLS) framework gives an efficient solution for training flat-structured feedforward networks and flat structured deep neural networks. However, the classical BLS model and other variants focus on the faultless situation only, where enhancement nodes, feature mapped nodes, and output weights of a BLS network are assumed to be realized in a perfect condition. When a trained BLS network suffers from coexistence of weight/node failures, the trained network has a greatly degradation in its performance if a countermeasure is not taken. In order to reduce the effect of weight/node failures on the BLS network’s performance, this paper proposes an objective function for enhancing the fault aware performance of BLS networks. The objective function contains a fault aware regularizer term which handles the weight/node failures. A learning algorithm is then derived based on the objective function. The simulation results show that the performance of the proposed fault aware BLS (FABLS) algorithm is superior to the classical BLS and two state-of-the-arts BLS algorithms, namely correntropy criterion BLS (CBLS) and weighted BLS (WBLS).

In recent years there has been a significant rethinking of corporate management, which is increasingly based on customer orientation principles. As a matter of fact, customer relationship management processes and systems are ever more popular and crucial to facing today’s business challenges. However, the large number of available customer communication stimuli coming from different (direct and indirect) channels, require automatic language processing techniques to help filter and qualify such stimuli, determine priorities, facilitate the routing of requests and reduce the response times. In this scenario, sentiment analysis plays an important role in measuring customer satisfaction, tracking consumer opinion, interacting with consumers and building customer loyalty. The research described in this paper proposes an approach based on Hierarchical Attention Networks for detecting the sentiment polarity of customer communications. Unlike other existing approaches, after initial training, the defined model can improve over time during system operation using the feedback provided by CRM operators thanks to an integrated incremental learning mechanism. The paper also describes the developed prototype as well as the dataset used for training the model which includes over 30.000 annotated items. The results of two experiments aimed at measuring classifier performance and validating the retraining mechanism are also presented and discussed. In particular, the classifier accuracy turned out to be better than that of other algorithms for the supported languages (macro-averaged f1-score of 0.89 and 0.79 for Italian and English respectively) and the retraining mechanism was able to improve the classification accuracy on new samples without degrading the overall system performance.

Attracted by the advantages of support vector regression and incremental learning approach, it is proposed in this work that an incremental support vector regression (ISVR) model optimized by particle swarm optimization (PSO) algorithm, and some improvements are made to be more suitable for sensor faults on-line diagnosis. To reducethe training time of ISVR model, an optimal training subset (OTS) method is adopted to reduce the size of training data set of the model. Then, in order to solve the problem of slow convergence of standard PSO algorithm, an incremental PSO (IPSO) algorithm is proposed to accelerate the model convergence through adjusting the inertial weight of each particle, which is gained by comparing the current position of each particle and the optimal position of the last incremental training. Based on the above improvements, a hybrid model, IPSO-OTS-ISVR model is presented finally. Experimental results based on actual operational data of a gas turbine shows that, under the premise of ensuring accuracy, the proposed IPSO-OTS-ISVR has much better performance in model response time and convergence performance over the comparison models. The experimental results based on an UCI data set indicate that the proposed hybrid model can also be extended to solve other prediction problems.

Supervised training of a deep neural network for semantic segmentation of point clouds requires a large amount of labelled data. Nowadays, it is easy to acquire a huge number of points with high density in large-scale areas using current LiDAR and photogrammetric techniques. However it is extremely time-consuming to manually label point clouds for model training. In this paper, we propose an active and incremental learning strategy to iteratively query informative point cloud data for manual annotation and the model is continuously trained to adapt to the newly labelled samples in each iteration. We evaluate the data informativeness step by step and effectively and incrementally enrich the model knowledge. The data informativeness is estimated by two data dependent uncertainty metrics (point entropy and segment entropy) and one model dependent metric (mutual information). The proposed methods are tested on two datasets. The results indicate the proposed uncertainty metrics can enrich current model knowledge by selecting informative samples, such as considering points with difficult class labels and choosing target objects with various geometries in the labelled training pool. Compared to random selection, our metrics provide valuable information to significantly reduce the labelled training samples. In contrast with training from scratch, the incremental fine-tuning strategy significantly save the training time.

Incremental Learning is a particular form of machine learning that enables a model to be modified incrementally, when new data becomes available. In this way, the model can adapt to the new data without the lengthy and time-consuming process required for complete model re-training. However, existing incremental learning methods face two significant problems: 1) noise in the classification sample data, 2) poor accuracy of modern classification algorithms when applied to modern classification problems. In order to deal with these issues, this paper proposes an integrated classification model, known as a Pre-trained Truncated Gradient Confidence-weighted (Pt-TGCW) model. Since the pre-trained model can extract and transform image information into a feature vector, the integrated model also shows its advantages in the field of image classification. Experimental results on ten datasets demonstrate that the proposed method outperform the original counterparts.

As an ensemble algorithm, network boosting enjoys a powerful classification ability but suffers from the tedious and time-consuming training process. To tackle the problem, in this paper, a broad network gradient boosting system (BNGBS) is developed by integrating gradient boosting machine with broad networks, in which the classification loss caused by a base broad network is learned and eliminated by followed networks in a cascade manner. The proposed system is constructed as an additive model and can be easily optimized by a greedy strategy instead of the tedious back-propagation algorithm, resulting in a more efficient learning process. Meanwhile, triple incremental learning capabilities including the increment of feature nodes, increment of input samples, and increment of target classes are designed. The proposed system can be efficiently updated and expanded based on the current status instead of being entirely retrained when the demands for more feature nodes, input samples, and target classes are proposed. The node-increment ability allows to add more feature nodes into the built system if the current structures are not effective for learning. The sample-increment ability is developed to allow the model to keep learning from the coming batch data. The class-increment ability is used to tackle the issue that the coming batch data may contain unseen categories. In comparison with existing popular machine learning methods, comprehensive results based on eight benchmark datasets illustrate the effectiveness of the proposed broad network gradient boosting system for the classification task.

For incremental machine-learning applications it is often important to robustly estimate the system accuracy during training, especially if humans perform the supervised teaching. Cross-validation and interleaved test/train error are here the standard supervised approaches. We propose a novel semi-supervised accuracy estimation approach that clearly outperforms these two methods. We introduce the Configram Estimation (CGEM) approach to predict the accuracy of any classifier that delivers confidences. By calculating classification confidences for unseen samples, it is possible to train an offline regression model, capable of predicting the classifier&rsquo, s accuracy on novel data in a semi-supervised fashion. We evaluate our method with several diverse classifiers and on analytical and real-world benchmark data sets for both incremental and active learning. The results show that our novel method improves accuracy estimation over standard methods and requires less supervised training data after deployment of the model. We demonstrate the application of our approach to a challenging robot object recognition task, where the human teacher can use our method to judge sufficient training.

Ensemble pruning can effectively overcome several shortcomings of the classical ensemble learning paradigm, such as the relatively high time and space complexity. However, each predictor has its own unique ability. One predictor may not perform well on some samples, but it will perform very well on other samples. Blindly underestimating the power of specific predictors is unreasonable. Choosing the best predictor set for each query sample is exactly what dynamic ensemble pruning techniques address. This paper proposes a hybrid Time Series Prediction (TSP) algorithm to implement one-step-ahead prediction task, integrating Dynamic Ensemble Pruning (DEP), Incremental Learning (IL), and Kernel Density Estimation (KDE), abbreviated as the EnsPKDEI 2) Dynamic Ensemble Pruning (DEP), achieved by one subalgorithm called EnsPKDE; 3) Incremental Learning (IL), realized by one subalgorithm termed IncLKDE. Benefited from the advantages of integrating Dynamic Ensemble Pruning scheme, Incremental Learning paradigm and Kernel Density Estimation, in the experimental results, EnsPKDE&IncLKDE demonstrates superior prediction performance to several other state-of-the-art algorithms in fulfilling time series forecasting tasks.

One of the most challenging problems in the field of online learning is concept drift, which deeply influences the classification stability of streaming data. If the data stream is imbalanced, it is even more difficult to detect concept drifts and make an online learner adapt to them. Ensemble algorithms have been found effective for the classification of streaming data with concept drift, whereby an individual classifier is built for each incoming data chunk and its associated weight is adjusted to manage the drift. However, it is difficult to adjust the weights to achieve a balance between the stability and adaptability of the ensemble classifiers. In addition, when the data stream is imbalanced, the use of a size-fixed chunk to build a single classifier can create further problems; the data chunk may contain too few or even no minority class samples (i.e., only majority class samples). A classifier built on such a chunk is unstable in the ensemble. In this article, we propose a chunk-based incremental learning method called adaptive chunk-based dynamic weighted majority (ACDWM) to deal with imbalanced streaming data containing concept drift. ACDWM utilizes an ensemble framework by dynamically weighting the individual classifiers according to their classification performance on the current data chunk. The chunk size is adaptively selected by statistical hypothesis tests to access whether the classifier built on the current data chunk is sufficiently stable. ACDWM has four advantages compared with the existing methods as follows: 1) it can maintain stability when processing nondrifted streams and rapidly adapt to the new concept; 2) it is entirely incremental, i.e., no previous data need to be stored; 3) it stores a limited number of classifiers to ensure high efficiency; and 4) it adaptively selects the chunk size in the concept drift environment. Experiments on both synthetic and real data sets containing concept drift show that ACDWM outperforms both state-of-the-art chunk-based and online methods.

The emergence of a massive Internet-of-Things (IoT) ecosystem is changing the human lifestyle. In several practical scenarios, IoT still faces significant challenges with reliance on human assistance and unacceptable response time for the treatment of big data. Therefore, it is very urgent to establish a new framework and algorithm to solve problems specific to this kind of fast autonomous IoT. Traditional reinforcement learning and deep reinforcement learning (DRL) approaches have abilities of autonomous decision making, but time-consuming modeling and training procedures limit their applications. To get over this dilemma, this article proposes the broad reinforcement learning (BRL) approach that fits fast autonomous IoT as it combines the broad learning system (BLS) with a reinforcement learning paradigm to improve the agent’s efficiency and accuracy of modeling and decision making. Specifically, a BRL framework is first constructed. Then, the associated learning algorithm, containing training pool introduction, training sample preparation, and incremental learning for BLS, is carefully designed. Finally, as a case study of fast autonomous IoT, the proposed BRL approach is applied to traffic light control, aiming to alleviate traffic congestion in the intersections of smart cities. The experimental results show that the proposed BRL approach can learn better action policy at a shorter execution time when compared with competing approaches.

When adding new tasks/classes in an incremental learning scenario, the previous recognition capabilities trained on the previous training data can be lost. In the real-life application of automatic target recognition (ATR), part of the previous samples may be able to be used. Most incremental learning methods have not considered how to save the previous key samples. In this article, the class boundary exemplar selection-based incremental learning (CBesIL) is proposed to save the previous recognition capabilities in the form of the class boundary exemplars. For exemplar selection, the class boundary selection method based on local geometrical and statistical information is proposed. And when adding new classes continually, a class-boundary-based data reconstruction method is introduced to update the exemplar set. Thus, when adding new classes, the previous class boundaries could be kept complete. Experimental results demonstrate that the proposed CBesIL outperforms the other state of the art on the accuracy of multiclass recognition and class-incremental recognition.

Fault diagnosis, which identifies the root cause of the observed out-of-control status, is essential to counteracting or eliminating faults in industrial processes. Many conventional data-driven fault diagnosis methods ignore the fault tendency of abnormal samples, and they need a complete retraining process to include the newly collected abnormal samples or fault classes. In this article, a broad convolutional neural network (BCNN) is designed with incremental learning capability for solving the aforementioned issues. The proposed method combines several consecutive samples as a data matrix, and it then extracts both fault tendency and nonlinear structure from the obtained data matrix by using convolutional operation. After that, the weights in fully connected layers can be trained based on the obtained features and their corresponding fault labels. Because of the architecture of this network, the diagnosis performance of the BCNN model can be improved by adding newly generated additional features. Finally, the incremental learning capability of the proposed method is also designed, so that the BCNN model can update itself to include new coming abnormal samples and fault classes. The proposed method is applied both to a simulated process and a real industrial process. Experimental results illustrate that it can better capture the characteristics of the fault process, and effectively update diagnosis model to include new coming abnormal samples, and fault classes.

In this paper, a data-driven predictive control strategy for nonlinear system is proposed and testified on a continuous stirred tank heater (CSTH) benchmark. A recursive modified partial least square (RMPLS) algorithm is employed to regress the local linear model. The algorithm of locally weighted projection regression (LWPR) is then leveraged to build the predictive model, based on which a novel data-driven predictive control strategy is put forward. The proposed predictive controller has the ability to deal with changing working conditions, benefiting from the incremental learning ability of RMPLS and LWPR. The performance of the proposed control strategy is demonstrated with the CSTH while the superiority is illustrated by comparison with an existing model-free adaptive control approach.

The Denoising Autoencoder (DAE) enhances the flexibility of the data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves an in-depth study because it characterizes a fixed network capacity that cannot adapt to rapidly changing environments. Deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. It features an open structure in the generative phase and the discriminative phase where the hidden units can be automatically added and discarded on the fly. The generative phase refines the predictive performance of the discriminative model exploiting unlabeled data. Furthermore, DEVDAN is free of the problem-specific threshold and works fully in the single-pass learning fashion. We show that DEVDAN can find competitive network architecture compared with state-of-the-art methods on the classification task using ten prominent datasets simulated under the prequential test-then-train protocol., This paper has been accepted for publication in Neurocomputing 2019. arXiv admin note: substantial text overlap with arXiv:1809.09081

General fuzzy min-max (GFMM) neural network is a generalization of fuzzy neural networks formed by hyperbox fuzzy sets for classification and clustering problems. Two principle algorithms are deployed to train this type of neural network, i.e., incremental learning and agglomerative learning. This paper presents a comprehensive empirical study of performance influencing factors, advantages, and drawbacks of the general fuzzy min-max neural network on pattern classification problems. The subjects of this study include (1) the impact of maximum hyperbox size, (2) the influence of the similarity threshold and measures on the agglomerative learning algorithm, (3) the effect of data presentation order, (4) comparative performance evaluation of the GFMM with other types of fuzzy min-max neural networks and prevalent machine learning algorithms. The experimental results on benchmark datasets widely used in machine learning showed overall strong and weak points of the GFMM classifier. These outcomes also informed potential research directions for this class of machine learning algorithms in the future., Comment: 18 pages, 7 figures, 12 tables

Information security is an important research area. As a very special yet important case, malware classification plays an important role in information security. In the real world, the malware datasets are open-ended and dynamic, and new malware samples belonging to old classes and new classes are increasing continuously. This requires the malware classification method to enable incremental learning, which can efficiently learn the new knowledge. However, existing works mainly focus on feature engineering with machine learning as a tool. To solve the problem, we present an incremental malware classification framework, named “IMC,” which consists of opcode sequence extraction, selection, and incremental learning method. We develop an incremental learning method based on multiclass support vector machine (SVM) as the core component of IMC, named “IMCSVM,” which can incrementally improve its classification ability by learning new malware samples. In IMC, IMCSVM adds the new classification planes (if new samples belong to a new class) and updates all old classification planes for new malware samples. As a result, IMC can improve the classification quality of known malware classes by minimizing the prediction error and transfer the old model with known knowledge to classify unknown malware classes. We apply the incremental learning method into malware classification, and the experimental results demonstrate the advantages and effectiveness of IMC.

Valid prediction of blood glucose concentration can help people to manage diabetes mellitus, alert hypoglycemia/hyperglycemia, exploit artificial pancreas, and plan a treatment program. Along the development of continuous glucose monitoring system (CGMS), the massive historical data require a new modeling framework based on a data-driven perspective. Studies indicate that the glucose time series (i.e., CGMS readings) involve chaotic properties; therefore, echo state networks (ESN) and its improved variants are proposed to establish subject-specific prediction models owing to their superiority in processing chaotic systems. This study mainly has two innovations: (1) a novel combination of incremental learning and ESN is developed to obtain a suitable network structure through partial optimization of parameters; (2) a feedback ESN is proposed to excavate the relationship of different predictions. These methods are assessed on ten patients with diabetes mellitus. Experimental results substantiate that the proposed methods achieve superior prediction performance in terms of four evaluation metrics compared with three conventional methods.

Semi-supervised learning (SSL) typically involves a small quantity of labeled data and a large quantity of unlabeled data. As such, the successful application of semi-supervised learning (SSL) depends on distinguishing easy and hard samples which contributes substantial recognition, as well as obtaining a more accurate pseudo target for a hard sample. However, existing SSL network models with deeper layers will suffer from overfitting or optimization difficulties. To address these problems, we propose a growing network (GrowingNet) where the convolution depth of the model can expand and contract. We also propose an incremental learning method by which the amount of pseudo labeled data can be increased uniformly. During training, the goal is to increase the convolutional layers of our model and the number of pseudo labeled data synchronously. We divide training epochs, the convolutional layers of GrowingNet, and pseudo labeled data into u equal parts. During each part of training epochs, we increase one part of convolutional layers, select one division of pseudo labeled data into the training process. The accuracy of the model will improve as training progresses, which distinguishes easy and hard samples and also provides more reliable pseudo labels during subsequent part of training epochs. This provides significant improvements over state-of-the-art networks in most of cases on SSL benchmark tasks (CIFAR-10, CIFAR-100, and SVHN). Specifically, without data augmentation, our model produces error rates of 20.86%, 18.22%, and 12.02% on CIFAR-10 with 1000, 2000, and 4000 labeled data, as well as error rates of 5.03% and 3.46% on SVHN with 500 and 1000 labeled data, respectively. With data augmentation, the error rate reaches 12.16% on CIFAR-10 with 2000 labeled data and 31.06% on CIFAR-100 with 10,000 labeled data.

The notion of a most specific consequence with respect to some terminological box is introduced, conditions for its existence in the description logic E L and its variants are provided, and means for its computation are developed. Algebraic properties of most specific consequences are explored. Furthermore, several applications that make use of this new notion are proposed and, in particular, it is shown how given terminological knowledge can be incorporated in existing approaches for the axiomatization of observations. For instance, a procedure for an incremental learning of concept inclusions from sequences of interpretations is developed.

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both funding and expertise. By selecting unlabeled examples that are promising in terms of model improvement and only asking for respective labels, active learning can increase the efficiency of the labeling process in terms of time and cost. In this work, we describe combinations of an incremental learning scheme and methods of active learning. These allow for continuous exploration of newly observed unlabeled data. We describe selection criteria based on model uncertainty as well as expected model output change (EMOC). An object detection task is evaluated in a continuous exploration context on the PASCAL VOC dataset. We also validate a weakly supervised system based on active and incremental learning in a real-world biodiversity application where images from camera traps are analyzed. Labeling only 32 images by accepting or rejecting proposals generated by our method yields an increase in accuracy from 25.4% to 42.6%., Comment: Accepted for publication in KI - K\"unstliche Intelligenz

Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data demands high computational time and energy requirements. Also, previously seen training samples may not be available at the time of retraining. We propose an efficient training methodology and incrementally growing DCNN to learn new tasks while sharing part of the base network. Our proposed methodology is inspired by transfer learning techniques, although it does not forget previously learned tasks. An updated network for learning new set of classes is formed using previously learned convolutional layers (shared from initial part of base network) with addition of few newly added convolutional kernels included in the later layers of the network. We employed a `clone-and-branch' technique which allows the network to learn new tasks one after another without any performance loss in old tasks. We evaluated the proposed scheme on several recognition applications. The classification accuracy achieved by our approach is comparable to the regular incremental learning approach (where networks are updated with new training samples only, without any network sharing), while achieving energy efficiency, reduction in storage requirements, memory access and training time., Comment: 18 pages, 13 figures. IEEE Access 2019

Generally, in-the-wild emotions are complex in nature. They often occur in combinations of multiple basic emotions, such as fear, happy, disgust, anger, sadness and surprise. Unlike the basic emotions, annotation of complex emotions, such as pain, is a time-consuming and expensive exercise. Moreover, there is an increasing demand for profiling such complex emotions as they are useful in many real-world application domains, such as medical, psychology, security and computer science. The traditional emotion recognition systems require a significant amount of annotated training samples to understand the complex emotions. This limits the direct applicability of those methods for complex emotion detection from images and videos. Therefore, it is important to learn the profile of the in-the-wild complex emotions accurately using limited annotated samples. In this paper, we propose a deep framework to incrementally and actively profile in-the-wild complex emotions, from sparse data. Our approach consists of three major components, namely a pre-processing unit, an optimization unit and an active learning unit. The pre-processing unit removes the variations present in the complex emotion images extracted from an uncontrolled environment. Our novel incremental active learning algorithm along with an optimization unit effectively predicts the complex emotions present in-the-wild. Evaluation using multiple complex emotions benchmark datasets reveals that our proposed approach performs close to the human perception capability in effectively profiling complex emotions. Further, our proposed approach shows a significant performance enhancement, in comparison with the state-of-the-art deep networks and other benchmark complex emotion profiling approaches.

Class incremental learning is an online learning paradigm wherein the classes to be recognized are gradually increased with limited memory, storing only a partial set of examples of past tasks. At a task transition, we observe an unintentional imbalance of confidence or likelihood between the classes of the past and the new task. We argue that the imbalance aggravates a catastrophic forgetting for class incremental learning. We propose a simple yet effective learning objective to balance the confidence of classes of old tasks and new task in the class incremental learning setup. In addition, we compare various sample memory configuring strategies and propose a novel sample memory management policy to alleviate the forgetting further. The proposed method outperforms the state of the arts in many evaluation metrics including accuracy and forgetting $F$ by a large margin (up to 5.71% in $A_{10}$ and 17.1% in $F_{10}$ ) in extensive empirical validations on multiple visual recognition datasets such as CIFAR100, TinyImageNet and a subset of the ImageNet.

The existing inverse-free incremental learning algorithm for the regularized extreme learning machine (ELM) was based on an inverse-free algorithm to update the regularized pseudo-inverse, which was deduced from an inverse-free recursive algorithm to update the inverse of a Hermitian matrix. Before that recursive algorithm was applied in the existing inverse-free ELM, its improved version had been utilized in previous literatures. Then from the improved recursive algorithm to update the inverse, we deduce a more efficient inverse-free algorithm to update the regularized pseudo-inverse, from which we propose the inverse-free incremental ELM algorithm based on regularized pseudo-inverse. Usually the above-mentioned inverse is smaller than the pseudo-inverse, while in the processor units with limited precision, the recursive algorithm to update the inverse may introduce numerical instabilities. Then to further reduce the computational complexity, we also propose the inverse-free incremental ELM algorithm based on the ${\mathrm {LDL}}^{T}$ factors of the inverse, where the ${\mathrm {LDL}}^{T}$ factors are updated iteratively by the inverse ${\mathrm {LDL}}^{T}$ factorization. With respect to the existing inverse-free ELM, the proposed ELM based on regularized pseudo-inverse and that based on ${\mathrm {LDL}}^{T}$ factors are expected to require only $\frac {3}{8+M}$ and $\frac {1}{8+M}$ of complexities, respectively, where $M$ is the output node number. The numerical experiments show that both the proposed ELM algorithms significantly accelerate the existing inverse-free ELM, and the speedup in training time is not less than 1.41. On the Modified National Institute of Standards and Technology (MNIST) Dataset, usually the proposed algorithm based on ${\mathrm {LDL}}^{T}$ factors is much faster than that based on regularized pseudo-inverse. On the other hand, in the numerical experiments, the original ELM, the existing inverse-free ELM and the proposed two ELM algorithms achieve the same performance in regression and classification, and result in the same solutions, which include the output weights and the output sequence for the same input sequence.

The technological advancement in VoIP technology and P2P streaming led to the development of novel applications. Most of these applications use UDP traffic. The availability of UDP services for applications such as streaming, trivial file transfer, are denied to legitimate users due to malicious traffic, intentionally created by abnormal requesting behaviour of the botnets. Categorizing the traffic is required to discriminate the malicious traffic that occur due to attacks from normal traffic for better real time resource allocation. For this purpose, this paper proposes a two level hybrid classification model based on incremental learning to detect high and low rate attacks that deny the legitimate access to connectionless services. The simulation results show that the proposed incremental learning strategy improves the classification accuracy of the proposed hybrid classifier compared to existing traditional learning methods.

Over the past decade, Deep Convolutional Neural Networks (DCNNs) have shown remarkable performance in most computer vision tasks. These tasks traditionally use a fixed dataset, and the model, once trained, is deployed as is. Adding new information to such a model presents a challenge due to complex training issues, such as "catastrophic forgetting", and sensitivity to hyper-parameter tuning. However, in this modern world, data is constantly evolving, and our deep learning models are required to adapt to these changes. In this paper, we propose an adaptive hierarchical network structure composed of DCNNs that can grow and learn as new data becomes available. The network grows in a tree-like fashion to accommodate new classes of data, while preserving the ability to distinguish the previously trained classes. The network organizes the incrementally available data into feature-driven super-classes and improves upon existing hierarchical CNN models by adding the capability of self-growth. The proposed hierarchical model, when compared against fine-tuning a deep network, achieves significant reduction of training effort, while maintaining competitive accuracy on CIFAR-10 and CIFAR-100., Comment: 8 pages, 6 figures, 7 tables Accepted in Neural Networks, 2019

Learning streaming data with limited size of memory storage becomes an interesting problem. Although there have been several learning methods recently proposed, based on the interesting concept of discard-after-learn , the performance of these issues: the learning speed, number of redundant neurons, and classification accuracy of these methods can be further improved in terms of faster speed, less number of neurons, and higher accuracy. The following new concepts and approaches were proposed in this paper: (1) a more generic structure of hyper-ellipsoidal function called Scalable Hyper-Ellipsoidal Function (SHEF) capable of handling the problem of a curse of dimensionality by introducing a regularization parameter into the covariance matrix of SHEF; (2) a new recursive function to update the covariance matrix of SHEF based on only the incoming data chunk; (3) a fast and easy conditions to test the states of being overlapped, inside, and touching of two SHEFs; (4) a new distance measure for determining the class of a queried datum based on the projected distance on only one discriminant vector, namely the Projection Ratio . The experimental results show the significant improvement when compared with the results from VLLDA, ILDA, LOL, VEBF, and CIL in terms of classification accuracy, the number of generated neurons, and computational time.

A non-iterative learning algorithm for artificial neural networks is an alternative to optimize the neural network parameters with extremely fast convergence time. Extreme learning machine (ELM) is one of the fastest learning algorithms based on a non-iterative method for a single hidden layer feedforward neural network (SLFN) model. ELM uses a randomization technique that requires a large number of hidden nodes to achieve the high accuracy. This leads to a large and complex model, which is slow at the inference time. Previously, we reported analytical incremental learning (AIL) algorithm, which is a compact model and a non-iterative deterministic learning algorithm, to be used as an alternative. However, AIL cannot grow its set of hidden nodes, due to the node saturation problem. Here, we describe a local sigmoid method (LSM) that is also a sufficiently compact model and a non-iterative deterministic learning algorithm to overcome both the ELM randomization and AIL node saturation problems. The LSM algorithm is based on “divide and conquer” method that divides the dataset into several subsets which are easier to optimize separately. Each subset can be associated with a local segment represented as a hidden node that preserves local information of the subset. This technique helps us to understand the function of each hidden node of the network built. Moreover, we can use such a technique to explain the function of hidden nodes learned by backpropagation, the iterative algorithm. Based on our experimental results, LSM is more accurate than other non-iterative learning algorithms and one of the most compact models.

In recent years, in the field of education technology, artificial intelligence tutors have come to be expected to provide individualized educational services to help learners achieve high levels of academic success. To this end, AI tutors need to be able to understand the current status and preferences of a learner and then suggest appropriate learning contents accordingly. However, it is challenging to monitor learner status and preferences continually and to recommend appropriate educational services. In this paper, we propose an individualized AI tutor as an integrated system of three developmental learning networks (DLNs) by extending a deep adaptive resonance theory (Deep ART) network, a neural network capable of incremental learning. Specifically, the learner status DLN is able to easily add new input channels about learner status without disrupting existing classifiers. The learner preference DLN is to categorize learner preferences based on frequency as well as sequence of events. The learner experience DLN is updated to immediately reflect alteration of the educational effectiveness in the current classification. Our AI tutor is currently embedded in a commercialized mobile application for teaching the Korean language to children. Experimental results show that the AI tutor application efficiently helps children learn the Korean language.

In this paper, a visual focus of attention (VFOA) detection method based on the improved hybrid incremental dynamic Bayesian network (IHIDBN) constructed with the fusion of head, gaze and prediction sub-models is proposed aiming at solving the problem of the complexity and uncertainty in dynamic scenes. Firstly, gaze detection sub-model is improved based on the traditional human eye model to enhance the recognition rate and robustness for different subjects which are detected. Secondly, the related sub-models are described, and conditional probability is used to establish regression models respectively. Also an incremental learning method is used to dynamically update the parameters to improve adaptability of this model. The method has been evaluated on two public datasets and daily experiments. The results show that the method proposed in this paper can effectively estimate VFOA from user, and it is robust to the free deflection of the head and distance change.

Catastrophic forgetting is a key challenge for class-incremental learning with deep neural networks, where the performance decreases considerably while dealing with long sequences of new classes. To tackle this issue, in this paper, we propose a new exemplar-supported representation for incremental learning (ESRIL) approach that consists of three components. First, we use memory aware synapses (MAS) pre-trained on the ImageNet to retain the ability of robust representation learning and classification for old classes from the perspective of the model. Second, exemplar-based subspace clustering (ESC) is utilized to construct the exemplar set, which can keep the performance from various views of the data. Third, the nearest class multiple centroids (NCMC) is used as the classifier to save the training cost of the fully connected layer of MAS when the criterion is met. Intensive experiments and analyses are presented to show the influence of various backbone structures and the effectiveness of different components in our model. Experiments on several general-purpose and fine-grained image recognition datasets have fully demonstrated the efficacy of the proposed methodology.

Recent breakthroughs in computer vision areas, ranging from detection, segmentation, to classification, rely on the availability of large-scale representative training datasets. Yet, robotic vision poses new challenges towards applying visual algorithms developed from these datasets because the latter implicitly assume a fixed set of categories and time-invariant distribution of tasks. In practice, assistive robots should be able to operate in dynamic environments with everyday changes. The variations of four commonly observed factors, including illumination, occlusion, camera-object distance/angles and clutter, could make lifelong/continual learning in computer vision more challenging. Large-scale datasets previously made publicly available were relatively simple, and rarely include such real-world challenges in data collection. Benefited from the recent released OpenLORIS-Object dataset, which explicitly includes these real-world challenges in the lifelong object recognition task, we evaluate three most adopted regularization methods in lifelong/continual learning (Learning without Forgetting, Elastic Weights Consolidation, and Synaptic Intelligence). Their performances were compared with the naive and cumulative training modes as the lower bound and upper bound of performances, respectively. The experiments conducted on the dataset focused on task incremental learning, i.e., incremental difficulty based on the four environment of factors. However, all the three most reported lifelong/continual learning algorithms have failed with the increase in encountered batches across various metrics with indistinguishable performance comparing to the naive training mode. Our results highlight the current challenges in lifelong object recognition for assistive robots to operate in real-world dynamic scene.

In the analysis of real-world data, it is useful to learn a latent variable model that represents the data generation process. In this setting, latent tree models are useful because they are able to capture complex relationships while being easily interpretable. In this paper, we propose two incremental algorithms for learning forests of latent trees. Unlike current methods, the proposed algorithms are based on the variational Bayesian framework, which allows them to introduce uncertainty into the learning process and work with mixed data. The first algorithm, incremental learner , determines the forest structure and the cardinality of its latent variables in an iterative search process. The second algorithm, constrained incremental learner , modifies the previous method by considering only a subset of the most prominent structures in each step of the search. Although restricting each iteration to a fixed number of candidate models limits the search space, we demonstrate that the second algorithm returns almost identical results for a small fraction of the computational cost. We compare our algorithms with existing methods by conducting a comparative study using both discrete and continuous real-world data. In addition, we demonstrate the effectiveness of the proposed algorithms by applying them to data from the 2018 Spanish Living Conditions Survey. All code, data, and results are available at https://github.com/ferjorosa/incremental-latent-forests .

In the past few years, kernel-based one-class extreme learning machine (ELM) receives quite a lot of attention by researchers for offline/batch learning due to its noniterative and fast learning capability. This paper extends this concept for adaptive online learning with regularized kernel-based one-class ELM classifiers for detection of outliers, and are collectively referred to as ORK-OCELM. Two frameworks, viz., boundary and reconstruction, are presented to detect the target class in ORK-OCELM. The kernel hyperplane-based baseline one-class ELM model considers whole data in a single chunk, however, the proposed one-class classifiers are adapted in an online fashion from the stream of training samples. The performance of ORK-OCELM is evaluated on a standard benchmark as well as synthetic datasets for both types of environments, i.e., stationary and nonstationary. While evaluating on stationary datasets, these classifiers are compared against batch learning-based one-class classifiers. Similarly, while evaluating on nonstationary datasets, the comparison is done with incremental learning-based online one-class classifiers. The results indicate that the proposed classifiers yield better or similar outcomes for both. In the nonstationary dataset evaluation, adaptability of the proposed classifiers in a changing environment is also demonstrated. It is further shown that the proposed classifiers have large stream data handling capability even under limited system memory. Moreover, the proposed classifiers gain significant time improvement compared to traditional online one-class classifiers (in all aspects of training and testing). A faster learning ability of the proposed classifiers makes them more suitable for real-time anomaly detection.

Class-incremental learning is a model learning technique that can help classification models incrementally learn about new target classes and realize knowledge accumulation. It has become one of the major concerns of the machine learning and classification community. To overcome the catastrophic forgetting that occurs when the network is trained sequentially on a multi-class data stream, a double consolidation class-incremental learning (DCCIL) method is proposed. In the incremental learning process, the network parameters are adjusted by combining knowledge distillation and elastic weight consolidation, so that the network can better maintain the recognition ability of the old classes while learning the new ones. The incremental learning experiment is designed, and the proposed method is compared with the popular incremental learning methods such as EWC, LwF, and iCaRL. Experimental results show that the proposed DCCIL method can achieve better incremental accuracy than that of the current popular incremental learning algorithms, which can effectively improve the expansibility and intelligence of the classification model.

At present, cloud robots tend to be intelligent and cooperative. Based on this, we proposed a teaching method based on Imitation and a learning method that incorporates Incremental Learning and Meta Learning. We use Imitation Learning to teach robots, and more concretely, we propose a natural teaching method based on visual sense by using a depth camera, the robot can learn from the trajectory caught by the camera. Meta Learning helps robots understand the task and split it into some subtasks which enhances the level of generalization. Besides, once the circumstances change the robot can update the cloud database using Incremental Learning. Using proposed method, we make robots capable of learning and cooperating with other robots. It is no longer necessary for robots to learn based on a great number of data which is a shortcoming of traditional robots. The greatest advantage of this method is that we improve the learning efficiency of robots and enhance the level of generalization of the model. Our method was experimentally verified in a laboratory and the results indicated that the method improved the learning efficiency of robots.